8 citations · 18 across the 16 of their papers we have counts for
17 papers
When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP
Shota Sato, Hajime Kiyama, Tosho Hirasawa +1
Reducing the modality gap between image and text representations in CLIP is widely expected to improve cross-modal alignment and downstream performance. However, a smaller average…
HalDec-Bench: Benchmarking Hallucination Detector in Image Captioning
Kuniaki Saito, Risa Shinoda, Shohei Tanaka +3
Hallucination detection in captions (HalDec) assesses a vision-language model's ability to correctly align image content with text by identifying errors in captions that misreprese…
Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge
Yuzheng Xu, Tosho Hirasawa, Tadashi Kozuno +1
Large language models are widely employed as evaluators, a paradigm commonly referred to as LLM-as-a-judge. Prior research has predominantly examined point-wise or pair-wise evalua…
WarrantScore: Modeling Warrants between Claims and Evidence for Substantiation Evaluation in Peer Reviews
Kiyotada Mori, Shohei Tanaka, Tosho Hirasawa +3
The scientific peer-review process is facing a shortage of human resources due to the rapid growth in the number of submitted papers. The use of language models to reduce the human…
Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation
Huaying Zhang, Atsushi Hashimoto, Tosho Hirasawa
Skilled human interviewers can extract valuable information from experts. This raises a fundamental question: what makes some questions more effective than others? To address this,…
Assessing the Capabilities of LLMs in Humor:A Multi-dimensional Analysis of Oogiri Generation and Evaluation
Ritsu Sakabe, Hwichan Kim, Tosho Hirasawa +1
Computational humor is a frontier for creating advanced and engaging natural language processing (NLP) applications, such as sophisticated dialogue systems. While previous studies…